LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

PiVoT 10.7B Mistral V0.2 by maywell

 »  All LLMs  »  maywell  »  PiVoT 10.7B Mistral V0.2   URL Share it on

  687   

PiVoT 10.7B Mistral V0.2 is an open-source language model by maywell. Features: 10.7b LLM, VRAM: 21.4GB, Context: 32K, License: cc-by-sa-4.0, HF Score: 64.3, LLM Explorer Score: 0.13, Arc: 63.3, HellaSwag: 81.7, MMLU: 59.9, TruthfulQA: 58.2, WinoGrande: 80, GSM8K: 42.4.

  Conversational   Deploy:azure   En   Endpoints compatible   Ko   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/maywell/PiVoT-10.7B-Mistral-v0.2 

PiVoT 10.7B Mistral V0.2 Benchmarks

ARC: 63.31 vs 96.7 (so35)-34.5%
HellaSwag: 81.68 vs 95.3 (gpt4)-14.3%
MMLU: 59.86 vs 88.3 (so35)-32.2%
TruthfulQA: 58.23 vs 59 (gpt4)-1.3%
WinoGrande: 80.03 vs 87.5 (gpt4)-8.5%
GSM8K: 42.38 vs 96.4 (so35)-56%
LLME Score: 0.13365
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
PiVoT 10.7B Mistral V0.2 (maywell/PiVoT-10.7B-Mistral-v0.2)
🌟 Advertise your project 🚀

PiVoT 10.7B Mistral V0.2 Parameters and Internals

Model Type 
text-generation
Additional Notes 
PivoT is a finetuned model based on a merge of Mistral 0.2.
Supported Languages 
en (English), ko (Korean)
Training Details 
Methodology:
SFT + DPO
LLM NamePiVoT 10.7B Mistral V0.2
Repository 🤗https://huggingface.co/maywell/PiVoT-10.7B-Mistral-v0.2 
Model Size10.7b
Required VRAM21.4 GB
Updated2026-03-29
Maintainermaywell
Model Typemistral
Model Files  4.9 GB: 1-of-5   5.0 GB: 2-of-5   4.9 GB: 3-of-5   4.9 GB: 4-of-5   1.7 GB: 5-of-5
Supported Languagesen ko
Model ArchitectureMistralForCausalLM
Licensecc-by-sa-4.0
Context Length32768
Model Max Length32768
Transformers Version4.36.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typebfloat16

Quantized Models of the PiVoT 10.7B Mistral V0.2

Model
Likes
Downloads
VRAM
PiVoT 10.7B Mistral V0.2 GGUF53054 GB
PiVoT 10.7B Mistral V0.2 GPTQ336 GB
PiVoT 10.7B Mistral V0.2 AWQ236 GB

Best Alternatives to PiVoT 10.7B Mistral V0.2

Best Alternatives
Context / RAM
Downloads
Likes
Barely Regal 10.7B32K / 21.5 GB190
Quintellect 10.7B32K / 21.4 GB223
Chikuma 10.7B32K / 21.4 GB1265
Multi Verse Model 10.7B32K / 21.5 GB51
Longcat 10.7B32K / 21.5 GB53
PrimaSumika 10.7B 128K32K / 21.5 GB121
... Loyal Mistral Maid 32K V0.2 A32K / 21.5 GB211
PiVoT 10.7B Mistral V0.2 RP32K / 21.4 GB5847
Chikuma 10.7B V232K / 21.4 GB310
Mark1 Revision 10.7B32K / 42.9 GB41
Note: green Score (e.g. "73.2") means that the model is better than maywell/PiVoT-10.7B-Mistral-v0.2.

Rank the PiVoT 10.7B Mistral V0.2 Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 52721 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer